Patentable/Patents/US-8340423
US-8340423

Enhancing digital image mosaics using region-statistics

PublishedDecember 25, 2012
Assigneenot available in USPTO data we have
Inventorsnot available in USPTO data we have
Technical Abstract

Methods and systems for updating mosaics of digital source images are disclosed. According to one embodiment, a method for updating a mosaic of digital source images includes segmenting the mosaic to regions, generating a plurality of region-statistics where each region-statistics correspond to image characteristics of one region, organizing the plurality of region-statistics in a database, and updating the mosaic using at least one target region-statistics from the organized plurality of region-statistics. Updating the mosaic can include color correcting. The method for updating a mosaic of digital source images can also includes optimizing the organized plurality of region-statistics, wherein the optimizing is based on one or more reference region-statistics from the organized plurality of region-statistics.

Patent Claims
20 claims

Legal claims defining the scope of protection, as filed with the USPTO.

1

1. A method for updating a mosaic of digital source images, comprising: (a) segmenting the mosaic to regions; (b) generating a plurality of region-statistics, wherein each of the plurality of region-statistics corresponds to image characteristics of a respective region; (c) organizing the plurality of region-statistics in a database; and (d) updating the mosaic using at least one target region-statistics from the organized plurality of region-statistics, wherein the updating the mosaic includes: determining a pixel in the mosaic to update; and updating the pixel based on the organized plurality of region-statistics, and wherein updating the pixel includes: selecting at least one target region from the regions; determining a correction from the at least one target region; interpolating the correction from the at least one target region; and applying the interpolated correction to the pixel, wherein steps (a)-(d) are executed using at least one processor.

2

2. The method of claim 1 , further comprising: (e) optimizing the organized plurality of region-statistics, wherein the optimizing is based on one or more reference region-statistics from the organized plurality of region-statistics.

3

3. The method of claim 2 , wherein step (e) comprises at least one of: filtering the organized plurality of region-statistics; and extrapolating from a first organized region-statistics to a second organized region-statistics, wherein the first and second organized region-statistics are from the organized plurality of region-statistics.

4

4. The method of claim 1 , wherein step (c) comprises: associating, in the database, a first organized region-statistics from the organized plurality of region-statistics with a reference region identification, wherein the reference region identification identifies a reference region.

5

5. The method of claim 1 , wherein step (b) comprises: determining a first region to be a reference region; and collecting region-statistics for the first region.

6

6. The method of claim 5 , wherein step (b) further comprises: updating region-statistics of a second region of said regions using the region-statistics of the first region.

7

7. The method of claim 1 , wherein the selecting is based on the distance from the pixel to the center of the at least one target region.

8

8. The method of claim 1 , wherein the correction comprises one or more separate corrections, wherein each of the one or more separate corrections applies to a different color band.

9

9. The method of claim 8 , wherein said each of the one or more separate corrections includes a scaling component and an offset component.

10

10. The method of claim 1 , wherein the correction comprises a linear correction.

11

11. The method of claim 1 , further comprising: (f) receiving digital source images; and (g) blending the digital source images to generate the mosaic.

12

12. The method of claim 1 , wherein the first region-statistics and the organized region-statistics comprise color statistics.

13

13. A system for updating a mosaic of digital images, comprising: at least one processor; a memory coupled to the at least one processor; and a region-statistics module configured to be executed by the at least one processor, the region-statistics module comprising: a scene segmenter configured to segment the mosaic to regions; a statistics collector configured to generate a plurality of region-statistics, wherein each of the plurality of region-statistics corresponds to image characteristics of a respective region; a statistics organizer configured to organize the plurality of region-statistics in a database; and a statistics updater configured to update the mosaic using at least one target region-statistics from the organized plurality of region-statistics, wherein the updating the mosaic includes: determining a pixel in the mosaic to update; and updating the pixel based on the organized plurality of region-statistics, and wherein updating the pixel includes: selecting at least one target region from the regions; determining a correction from the at least one target region; interpolating the correction from the at least one target region; and applying the interpolated correction to the pixel.

14

14. The system of claim 13 , wherein the region-statistics module further comprises: a statistics optimizer configured to optimize the organized plurality of region-statistics based on one or more reference region-statistics from the organized plurality of region-statistics.

15

15. The system of claim 13 , wherein the correction comprises one or more separate corrections, wherein each of the one or more separate corrections applies to a different color band.

16

16. The system of claim 15 , wherein said each of the one or more separate corrections includes a scaling component and an offset component.

17

17. A tangible computer program product comprising a non-transitory computer readable medium having computer program logic recorded thereon for causing at least one processor to: segment a mosaic of digital source images to regions; generate a plurality of region-statistics, wherein each of the plurality of region-statistics correspond to image characteristics of a respective region; organize the plurality of region-statistics in a database; and update the mosaic using at least one target region-statistics from the organized plurality of region-statistics, wherein the updating the mosaic includes: determining a pixel in the mosaic to update; and updating the pixel based on the organized plurality of region-statistics, and wherein updating the pixel includes: selecting at least one target region from the regions; determining a correction from the at least one target region; interpolating the correction from the at least one target region; and applying the interpolated correction to the pixel.

18

18. The tangible computer program product of claim 17 , wherein the computer program logic further causes the at least one processor to: optimize the organized plurality of region-statistics, wherein the optimizing is based on one or more reference region-statistics from the organized plurality of region-statistics.

19

19. The tangible computer program product of claim 17 , wherein the correction comprises one or more separate corrections, wherein each of the one or more separate corrections applies to a different color band.

20

20. The tangible computer program product of claim 19 , wherein said each of the one or more separate corrections includes a scaling component and an offset component.

Classification Codes (CPC)

Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.

Patent Metadata

Filing Date

September 29, 2009

Publication Date

December 25, 2012

Want to explore more patents?

Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.

Citation & reuse

Analysis on this page is generated by Patentable — an AI-powered patent intelligence platform. AI-generated summaries, explanations, and analysis may be reused with attribution and a visible link back to the canonical URL below. Patent abstracts and claims are USPTO public domain.

Cite as: Patentable. “Enhancing digital image mosaics using region-statistics” (US-8340423). https://patentable.app/patents/US-8340423

© 2026 Patentable. All rights reserved.

Patentable is a research and drafting-assistant tool, not a law firm, and does not provide legal advice. Documents we generate are drafts for review by a licensed patent attorney.